Image classification for Caltech101 | Airplanes, Motorbikes & Schooners dastaset!¶
import numpy as np
import os
import PIL
import PIL.Image
import tensorflow as tf
import tensorflow_datasets as tfds
import pathlib
import matplotlib.pyplot as plt
from tensorflow.keras import layers
from tensorflow.keras import Model, Input
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Rescaling, Dropout
from tensorflow.keras.models import Sequential
seed_value = 332
tf.keras.backend.clear_session()
from sklearn.metrics import classification_report, balanced_accuracy_score
import matplotlib as mpl
mpl.rcParams['figure.dpi'] = 300
# 1. Set `PYTHONHASHSEED` environment variable at a fixed value
import os
os.environ['PYTHONHASHSEED']=str(seed_value)
# 2. Set `python` built-in pseudo-random generator at a fixed value
import random
random.seed(seed_value)
# 3. Set `numpy` pseudo-random generator at a fixed value
import numpy as np
np.random.seed(seed_value)
# 4. Set `tensorflow` pseudo-random generator at a fixed value
import tensorflow as tf
tf.random.set_seed(seed_value)
#Note: Replace 'str_dir' with your path to data directory
str_dir = 'D:\Fall 2022\Data Mining_CSE 5334\Assignments\Assignment1\Data\caltech101_classification'
data_dir = pathlib.Path(str_dir)
image_count = len(list(data_dir.glob('*/*.jpg')))
print(f'Total number of images in dataset: {image_count}')
Total number of images in dataset: 1661
# visualizing sample from class: Airplanes
airplanes = list(data_dir.glob('airplanes/*'))
airplane_sample = PIL.Image.open(str(airplanes[2]))
airplane_sample
# visualizing sample from class: Motorbikes
motorbikes = list(data_dir.glob('Motorbikes/*'))
morobike_sample = PIL.Image.open(str(motorbikes[0]))
morobike_sample
# visualizing sample from class: Schooners
schooners = list(data_dir.glob('schooner/*'))
schooner_sample = PIL.Image.open(str(schooners[2]))
schooner_sample
#Data partitioning
batch_size = 32
img_height = 224
img_width = 224
train_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=seed_value,
image_size=(img_height, img_width),
batch_size=batch_size)
val_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=seed_value,
image_size=(img_height, img_width),
batch_size=batch_size)
class_names = ['Motorbikes','airplanes','schooner']
Found 1661 files belonging to 3 classes. Using 1329 files for training. Found 1661 files belonging to 3 classes. Using 332 files for validation.
#visualizing samples from each class
plt.figure(figsize=(10, 10))
for images, labels in train_ds.take(1):
for i in range(9):
ax = plt.subplot(3, 3, i + 1)
plt.imshow(images[i].numpy().astype("uint8"))
plt.title(class_names[labels[i]])
plt.axis("off")
#prefetching the data for efficient dataloading
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
#Here I am using keras sequential API. Later in this blog post, I will use keras functional API to build the model.
num_classes = len(class_names)
model = Sequential([
layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
layers.Conv2D(16, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(64, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy','sparse_categorical_accuracy'])
model.summary()
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
conv2d_2 (Conv2D) (None, 56, 56, 64) 18496
max_pooling2d_2 (MaxPooling (None, 28, 28, 64) 0
2D)
flatten (Flatten) (None, 50176) 0
dense (Dense) (None, 128) 6422656
dense_1 (Dense) (None, 3) 387
=================================================================
Total params: 6,446,627
Trainable params: 6,446,627
Non-trainable params: 0
_________________________________________________________________
#training
epochs =3
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
Epoch 1/3 42/42 [==============================] - 23s 542ms/step - loss: 0.8960 - accuracy: 0.7126 - sparse_categorical_accuracy: 0.7126 - val_loss: 0.1973 - val_accuracy: 0.9247 - val_sparse_categorical_accuracy: 0.9247 Epoch 2/3 42/42 [==============================] - 22s 527ms/step - loss: 0.0849 - accuracy: 0.9759 - sparse_categorical_accuracy: 0.9759 - val_loss: 0.1486 - val_accuracy: 0.9428 - val_sparse_categorical_accuracy: 0.9428 Epoch 3/3 42/42 [==============================] - 23s 560ms/step - loss: 0.0393 - accuracy: 0.9880 - sparse_categorical_accuracy: 0.9880 - val_loss: 0.1412 - val_accuracy: 0.9578 - val_sparse_categorical_accuracy: 0.9578
#visualizing the training results
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs_range = [1,2,3]
plt.figure(figsize=(8, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
# compute classification metrics , precision, recall, F1 score on validation data
y_pred = model.predict(val_ds)
score = tf.nn.softmax(y_pred)
predicted_labels = np.argmax(score,axis =1)
ls_val_labels =[]
for img,label in val_ds:
ls_val_labels.append(label)
correct_labels = tf.concat([item for item in ls_val_labels], axis = 0)
print(classification_report(correct_labels, predicted_labels, target_names=class_names))
11/11 [==============================] - 2s 121ms/step
precision recall f1-score support
Motorbikes 0.92 1.00 0.96 146
airplanes 0.99 0.92 0.96 167
schooner 1.00 0.95 0.97 19
accuracy 0.96 332
macro avg 0.97 0.96 0.96 332
weighted avg 0.96 0.96 0.96 332
Write a function to build 2D CNN model with given number of layers and dropout fraction. Note that here I am using keras functional API to build the 2D CNN model.
def make_model(num_layers, dropout_frac = 0):
layer_filters = [16, 32, 64,128,256]
num_classes = len(class_names)
inputs = Input(shape=(img_height, img_width, 3))
x = inputs
x = Rescaling(1./255, )(x)
for num in range(num_layers-1):
x = Conv2D(layer_filters[num], 3, padding='same', activation='relu')(x)
x = MaxPooling2D()(x)
x = Flatten()(x)
x = Dense(layer_filters[num+1], activation = 'relu')(x)
x = Dropout(dropout_frac)(x)
x = Dense(num_classes)(x)
model = Model(inputs = inputs,outputs = x)
model.summary()
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
return model
Create models with varying depth and plot the effect.
ls_num_layers = [2,3,4,5]
ls_val_accuracy =[]
ls_train_accuracy =[]
for i in ls_num_layers:
tf.keras.backend.clear_session()
m = make_model(i)
epochs =3
print(f'---------------------Training model with {i} layers------------------------')
history = m.fit(train_ds, validation_data=val_ds, epochs=epochs)
# compute classification metrics , precision, recall, F1 score on validation dataset
y_pred = m.predict(val_ds)
score = tf.nn.softmax(y_pred)
y_pred_train = m.predict(train_ds)
score_train = tf.nn.softmax(y_pred_train)
val_predicted_labels = np.argmax(score,axis =1)
train_predicted_labels = np.argmax(score_train, axis=1)
ls_val_labels =[]
for img,label in val_ds:
ls_val_labels.append(label)
ls_train_labels =[]
for img,label in train_ds:
ls_train_labels.append(label)
correct_labels_val = tf.concat([item for item in ls_val_labels], axis = 0)
correct_labels_train = tf.concat([item for item in ls_train_labels], axis = 0)
validation_accuracy = balanced_accuracy_score(correct_labels_val,val_predicted_labels)
train_accuracy = balanced_accuracy_score(correct_labels_train,train_predicted_labels)
ls_val_accuracy.append(validation_accuracy)
ls_train_accuracy.append(train_accuracy)
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
flatten (Flatten) (None, 200704) 0
dense (Dense) (None, 32) 6422560
dropout (Dropout) (None, 32) 0
dense_1 (Dense) (None, 3) 99
=================================================================
Total params: 6,423,107
Trainable params: 6,423,107
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 2 layers------------------------
Epoch 1/3
42/42 [==============================] - 10s 238ms/step - loss: 2.0677 - accuracy: 0.7788 - val_loss: 0.2086 - val_accuracy: 0.9217
Epoch 2/3
42/42 [==============================] - 10s 233ms/step - loss: 0.0957 - accuracy: 0.9684 - val_loss: 0.1131 - val_accuracy: 0.9729
Epoch 3/3
42/42 [==============================] - 10s 235ms/step - loss: 0.0274 - accuracy: 0.9917 - val_loss: 0.0578 - val_accuracy: 0.9789
11/11 [==============================] - 1s 73ms/step
42/42 [==============================] - 3s 78ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 3 layers------------------------
Epoch 1/3
42/42 [==============================] - 17s 406ms/step - loss: 2.0447 - accuracy: 0.7833 - val_loss: 0.2179 - val_accuracy: 0.9277
Epoch 2/3
42/42 [==============================] - 17s 407ms/step - loss: 0.0760 - accuracy: 0.9759 - val_loss: 0.0596 - val_accuracy: 0.9880
Epoch 3/3
42/42 [==============================] - 17s 409ms/step - loss: 0.0210 - accuracy: 0.9962 - val_loss: 0.0598 - val_accuracy: 0.9819
11/11 [==============================] - 1s 104ms/step
42/42 [==============================] - 5s 108ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
conv2d_2 (Conv2D) (None, 56, 56, 64) 18496
max_pooling2d_2 (MaxPooling (None, 28, 28, 64) 0
2D)
flatten (Flatten) (None, 50176) 0
dense (Dense) (None, 128) 6422656
dropout (Dropout) (None, 128) 0
dense_1 (Dense) (None, 3) 387
=================================================================
Total params: 6,446,627
Trainable params: 6,446,627
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 4 layers------------------------
Epoch 1/3
42/42 [==============================] - 22s 520ms/step - loss: 0.4726 - accuracy: 0.8405 - val_loss: 0.0914 - val_accuracy: 0.9759
Epoch 2/3
42/42 [==============================] - 22s 530ms/step - loss: 0.0330 - accuracy: 0.9925 - val_loss: 0.1635 - val_accuracy: 0.9488
Epoch 3/3
42/42 [==============================] - 21s 510ms/step - loss: 0.0288 - accuracy: 0.9902 - val_loss: 0.0229 - val_accuracy: 0.9880
11/11 [==============================] - 1s 125ms/step
42/42 [==============================] - 6s 140ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
conv2d_2 (Conv2D) (None, 56, 56, 64) 18496
max_pooling2d_2 (MaxPooling (None, 28, 28, 64) 0
2D)
conv2d_3 (Conv2D) (None, 28, 28, 128) 73856
max_pooling2d_3 (MaxPooling (None, 14, 14, 128) 0
2D)
flatten (Flatten) (None, 25088) 0
dense (Dense) (None, 256) 6422784
dropout (Dropout) (None, 256) 0
dense_1 (Dense) (None, 3) 771
=================================================================
Total params: 6,520,995
Trainable params: 6,520,995
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 5 layers------------------------
Epoch 1/3
42/42 [==============================] - 29s 668ms/step - loss: 0.4059 - accuracy: 0.8330 - val_loss: 0.1414 - val_accuracy: 0.9518
Epoch 2/3
42/42 [==============================] - 26s 627ms/step - loss: 0.0678 - accuracy: 0.9797 - val_loss: 0.0715 - val_accuracy: 0.9789
Epoch 3/3
42/42 [==============================] - 25s 594ms/step - loss: 0.0300 - accuracy: 0.9910 - val_loss: 0.1435 - val_accuracy: 0.9548
11/11 [==============================] - 2s 156ms/step
42/42 [==============================] - 6s 153ms/step
# Barplot -- effect of # of CNN layers VS Accuracy
layers = ['2', '3', '4', '5']
x = np.arange(len(layers))
width = 0.25
fig, ax = plt.subplots()
fig.set_figheight(4)
fig.set_figwidth(8)
rects1 = ax.bar(x - width/2, np.round(ls_val_accuracy,4), width, label='Validation')
rects2 = ax.bar(x + width/2, np.round(ls_train_accuracy,4), width, label='Train')
ax.set_ylabel('Accuracy')
ax.set_xlabel('Number of layers in CNN model')
ax.set_title('Number of CNN layers vs Accuracy')
ax.set_xticks(x, layers)
ax.set_ylim([0.93,1.008])
ax.legend()
ax.bar_label(rects1, padding=3)
ax.bar_label(rects2, padding=3)
fig.tight_layout()
plt.show()
num_layers = 3
ls_dropout_frac = [0.1,0.2,0.3,0.4,0.5,0.6,0.7]
ls_val_accuracy =[]
ls_train_accuracy =[]
for i in ls_dropout_frac:
tf.keras.backend.clear_session()
m = make_model(num_layers,i)
epochs =3
print(f'---------------------Training model with {i} drop out fraction ------------------------')
history = m.fit(train_ds, validation_data=val_ds, epochs=epochs)
# compute classification metrics , precision, recall, F1 score on validation dataset
y_pred = m.predict(val_ds)
score = tf.nn.softmax(y_pred)
y_pred_train = m.predict(train_ds)
score_train = tf.nn.softmax(y_pred_train)
val_predicted_labels = np.argmax(score,axis =1)
train_predicted_labels = np.argmax(score_train, axis=1)
ls_val_labels =[]
for img,label in val_ds:
ls_val_labels.append(label)
ls_train_labels =[]
for img,label in train_ds:
ls_train_labels.append(label)
correct_labels_val = tf.concat([item for item in ls_val_labels], axis = 0)
correct_labels_train = tf.concat([item for item in ls_train_labels], axis = 0)
validation_accuracy = balanced_accuracy_score(correct_labels_val,val_predicted_labels)
train_accuracy = balanced_accuracy_score(correct_labels_train,train_predicted_labels)
ls_val_accuracy.append(validation_accuracy)
ls_train_accuracy.append(train_accuracy)
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.1 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 23s 528ms/step - loss: 0.6212 - accuracy: 0.8187 - val_loss: 0.1763 - val_accuracy: 0.9398
Epoch 2/3
42/42 [==============================] - 22s 515ms/step - loss: 0.0741 - accuracy: 0.9782 - val_loss: 0.0702 - val_accuracy: 0.9759
Epoch 3/3
42/42 [==============================] - 18s 440ms/step - loss: 0.0182 - accuracy: 0.9962 - val_loss: 0.0225 - val_accuracy: 0.9880
11/11 [==============================] - 1s 116ms/step
42/42 [==============================] - 5s 120ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.2 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 18s 413ms/step - loss: 0.9059 - accuracy: 0.8277 - val_loss: 0.1255 - val_accuracy: 0.9639
Epoch 2/3
42/42 [==============================] - 17s 400ms/step - loss: 0.0680 - accuracy: 0.9812 - val_loss: 0.0649 - val_accuracy: 0.9759
Epoch 3/3
42/42 [==============================] - 17s 408ms/step - loss: 0.0274 - accuracy: 0.9932 - val_loss: 0.0597 - val_accuracy: 0.9759
11/11 [==============================] - 1s 111ms/step
42/42 [==============================] - 5s 112ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.3 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 18s 409ms/step - loss: 1.1329 - accuracy: 0.8209 - val_loss: 0.1679 - val_accuracy: 0.9488
Epoch 2/3
42/42 [==============================] - 17s 402ms/step - loss: 0.0930 - accuracy: 0.9729 - val_loss: 0.1178 - val_accuracy: 0.9729
Epoch 3/3
42/42 [==============================] - 17s 404ms/step - loss: 0.0445 - accuracy: 0.9895 - val_loss: 0.0737 - val_accuracy: 0.9729
11/11 [==============================] - 1s 107ms/step
42/42 [==============================] - 5s 117ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.4 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 18s 413ms/step - loss: 0.7376 - accuracy: 0.8420 - val_loss: 0.1725 - val_accuracy: 0.9398
Epoch 2/3
42/42 [==============================] - 17s 414ms/step - loss: 0.0921 - accuracy: 0.9729 - val_loss: 0.0740 - val_accuracy: 0.9789
Epoch 3/3
42/42 [==============================] - 18s 425ms/step - loss: 0.0466 - accuracy: 0.9857 - val_loss: 0.0442 - val_accuracy: 0.9849
11/11 [==============================] - 1s 109ms/step
42/42 [==============================] - 5s 116ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.5 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 19s 442ms/step - loss: 1.5438 - accuracy: 0.7381 - val_loss: 0.2373 - val_accuracy: 0.9307
Epoch 2/3
42/42 [==============================] - 17s 410ms/step - loss: 0.1430 - accuracy: 0.9586 - val_loss: 0.1224 - val_accuracy: 0.9518
Epoch 3/3
42/42 [==============================] - 18s 419ms/step - loss: 0.0654 - accuracy: 0.9767 - val_loss: 0.0743 - val_accuracy: 0.9669
11/11 [==============================] - 1s 105ms/step
42/42 [==============================] - 5s 112ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.6 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 18s 430ms/step - loss: 1.1325 - accuracy: 0.7570 - val_loss: 0.2676 - val_accuracy: 0.9066
Epoch 2/3
42/42 [==============================] - 22s 518ms/step - loss: 0.1932 - accuracy: 0.9533 - val_loss: 0.1072 - val_accuracy: 0.9699
Epoch 3/3
42/42 [==============================] - 18s 433ms/step - loss: 0.1228 - accuracy: 0.9631 - val_loss: 0.1223 - val_accuracy: 0.9488
11/11 [==============================] - 1s 106ms/step
42/42 [==============================] - 5s 113ms/step
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 0.7 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 19s 444ms/step - loss: 1.7336 - accuracy: 0.5847 - val_loss: 0.4060 - val_accuracy: 0.8765
Epoch 2/3
42/42 [==============================] - 19s 445ms/step - loss: 0.4270 - accuracy: 0.8269 - val_loss: 0.1878 - val_accuracy: 0.9157
Epoch 3/3
42/42 [==============================] - 18s 435ms/step - loss: 0.2824 - accuracy: 0.8789 - val_loss: 0.1541 - val_accuracy: 0.9187
11/11 [==============================] - 1s 107ms/step
42/42 [==============================] - 5s 115ms/step
# Barplot -- effect of # of CNN layers including dense layers VS Accuracy
dropout_frac = ['0.1','0.2','0.3','0.4','0.5','0.6','0.7']
x = np.arange(len(dropout_frac))
width = 0.25
fig, ax = plt.subplots()
fig.set_figheight(4)
fig.set_figwidth(8)
rects1 = ax.bar(x - width/2, np.round(ls_val_accuracy,3), width, label='Validation')
rects2 = ax.bar(x + width/2, np.round(ls_train_accuracy,3), width, label='Train')
ax.set_ylabel('Accuracy')
ax.set_xlabel('Dropout fraction')
ax.set_title('Dropout fraction vs Accuracy')
ax.set_xticks(x, dropout_frac)
ax.set_ylim([0.80,1.008])
ax.legend(fontsize = 8)
ax.bar_label(rects1, padding=3, fontsize = 6)
ax.bar_label(rects2, padding=3,fontsize = 6)
fig.tight_layout()
plt.show()
num_layers = 3
dropout_frac = 0.1
tf.keras.backend.clear_session()
m = make_model(num_layers,dropout_frac)
epochs =3
print(f'---------------------Training model with {num_layers} layers and {dropout_frac} drop out fraction ------------------------')
history = m.fit(train_ds, validation_data=val_ds, epochs=epochs)
# compute classification metrics , precision, recall, F1 score on validation dataset
y_pred = m.predict(val_ds)
score = tf.nn.softmax(y_pred)
predicted_labels = np.argmax(score,axis =1)
ls_val_labels =[]
for img,label in val_ds:
ls_val_labels.append(label)
correct_labels = tf.concat([item for item in ls_val_labels], axis = 0)
train_acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
rescaling (Rescaling) (None, 224, 224, 3) 0
conv2d (Conv2D) (None, 224, 224, 16) 448
max_pooling2d (MaxPooling2D (None, 112, 112, 16) 0
)
conv2d_1 (Conv2D) (None, 112, 112, 32) 4640
max_pooling2d_1 (MaxPooling (None, 56, 56, 32) 0
2D)
flatten (Flatten) (None, 100352) 0
dense (Dense) (None, 64) 6422592
dropout (Dropout) (None, 64) 0
dense_1 (Dense) (None, 3) 195
=================================================================
Total params: 6,427,875
Trainable params: 6,427,875
Non-trainable params: 0
_________________________________________________________________
---------------------Training model with 3 layers and 0.1 drop out fraction ------------------------
Epoch 1/3
42/42 [==============================] - 19s 441ms/step - loss: 1.5554 - accuracy: 0.8141 - val_loss: 0.1221 - val_accuracy: 0.9578
Epoch 2/3
42/42 [==============================] - 18s 423ms/step - loss: 0.0637 - accuracy: 0.9812 - val_loss: 0.1064 - val_accuracy: 0.9759
Epoch 3/3
42/42 [==============================] - 18s 422ms/step - loss: 0.0186 - accuracy: 0.9955 - val_loss: 0.0506 - val_accuracy: 0.9819
11/11 [==============================] - 1s 120ms/step
#visualizing the training results
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs_range = range(epochs)
plt.figure(figsize=(8, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
# compute classification metrics , precision, recall, F1 score on validation data
y_pred = m.predict(val_ds)
score = tf.nn.softmax(y_pred)
predicted_labels = np.argmax(score,axis =1)
ls_val_labels =[]
for img,label in val_ds:
ls_val_labels.append(label)
correct_labels = tf.concat([item for item in ls_val_labels], axis = 0)
print(classification_report(correct_labels, predicted_labels, target_names=class_names))
11/11 [==============================] - 1s 113ms/step
precision recall f1-score support
Motorbikes 0.97 1.00 0.98 146
airplanes 1.00 0.97 0.98 167
schooner 0.95 0.95 0.95 19
accuracy 0.98 332
macro avg 0.97 0.97 0.97 332
weighted avg 0.98 0.98 0.98 332